vishalp23 commited on
Commit
0e05ee1
1 Parent(s): f7325e5

New AutoFinetune: run: v0.3.0

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +17 -3
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +16 -20
special_tokens_map.json CHANGED
@@ -1,4 +1,11 @@
1
  {
 
 
 
 
 
 
 
2
  "cls_token": {
3
  "content": "[CLS]",
4
  "lstrip": false,
@@ -6,15 +13,22 @@
6
  "rstrip": false,
7
  "single_word": false
8
  },
 
 
 
 
 
 
 
9
  "mask_token": {
10
  "content": "[MASK]",
11
- "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "[PAD]",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
@@ -28,7 +42,7 @@
28
  "single_word": false
29
  },
30
  "unk_token": {
31
- "content": "[UNK]",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
  "cls_token": {
10
  "content": "[CLS]",
11
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "[MASK]",
25
+ "lstrip": true,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": {
31
+ "content": "<pad>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
 
42
  "single_word": false
43
  },
44
  "unk_token": {
45
+ "content": "<unk>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,22 +1,22 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,31 +32,27 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
 
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
 
 
 
47
  "mask_token": "[MASK]",
48
- "max_length": 512,
49
  "model_max_length": 512,
50
- "pad_to_multiple_of": null,
51
- "pad_token": "[PAD]",
52
- "pad_token_type_id": 0,
53
- "padding_side": "right",
54
  "sep_token": "[SEP]",
55
- "stride": 0,
56
- "strip_accents": null,
57
- "tokenize_chinese_chars": true,
58
- "tokenizer_class": "DistilBertTokenizer",
59
- "truncation_side": "right",
60
- "truncation_strategy": "longest_first",
61
- "unk_token": "[UNK]"
62
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<pad>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<unk>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "[MASK]",
37
+ "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
  "cls_token": "[CLS]",
47
  "do_lower_case": true,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "keep_accents": false,
51
  "mask_token": "[MASK]",
 
52
  "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "remove_space": true,
 
 
55
  "sep_token": "[SEP]",
56
+ "tokenizer_class": "AlbertTokenizer",
57
+ "unk_token": "<unk>"
 
 
 
 
 
58
  }